Layer-Wise Anomaly Detection in Directed Energy Deposition using High-Fidelity Fringe Projection Profilometry

• URL: http://arxiv.org/abs/2509.05327v1
• Date: Sun, 31 Aug 2025 02:26:18 GMT
• Title: Layer-Wise Anomaly Detection in Directed Energy Deposition using High-Fidelity Fringe Projection Profilometry
• Abstract summary: Directed energy deposition (DED), a metal additive manufacturing process, is highly susceptible to process-induced defects.<n>This work presents a build-height-synchronized fringe projection system for in-situ, layer-wise surface reconstruction of laser-DED components.
• Score: 4.4711260927475065
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Directed energy deposition (DED), a metal additive manufacturing process, is highly susceptible to process-induced defects such as geometric deviations, lack of fusion, and poor surface finish. This work presents a build-height-synchronized fringe projection system for in-situ, layer-wise surface reconstruction of laser-DED components, achieving a reconstruction accuracy of ${\pm}$46 ${\mu}$m. From the reconstructed 3D morphology, two complementary geometry-based point cloud metrics are introduced: local point density, which highlights poor surface finish, and normal-change rate, which identifies lack-of-fusion features. These methods enable automated, annotation-free identification of common deposition anomalies directly from reconstructed surfaces, without the need for manual labeling. By directly linking geometric deviation to defect formation, the approach enables precise anomaly localization and advances the feasibility of closed-loop process control. This work establishes fringe projection as a practical tool for micrometer-scale monitoring in DED, bridging the gap between process signatures and part geometry for certifiable additive manufacturing.

Related papers

• Integrated Laser Scanning and Image-Based Topology Optimization Techniques for Detection and Quantification of Visible and Subsurface Structural Defects [0.0]
  This study presents two complementary non-contact, vision-based approaches for the detection and quantitative characterization of defects in structural components.<n>The first approach employs high-resolution laser scanning to generate 3D point clouds of damaged steel specimens.<n>The second approach combines full-field surface deformation measurements obtained using 3D-DIC with finite element model updating and topology optimization.
  arXiv  Detail & Related papers  (2026-09-01T19:31:32Z)
• Sensor-Informed Per-Point Covariance for Structured-Light 3D Imaging [0.0]
  Per-point uncertainty models are important in structured-light 3D reconstruction for probabilistic registration, fusion, and quality assessment.<n>This paper presents a sensor-informed first-order method for constructing a per-point 3 x 3 covariance field from experimentally measured phase precision and calibrated mappings.
  arXiv  Detail & Related papers  (2026-08-11T13:05:22Z)
• Beyond Isotropic Assumptions: Continuity-Constrained Segmentation and GPU Morphometry for Nanoscale GBM Analysis [1.3107669223114085]
  Confocal microscopy of optically cleared and swelled tissue resolves complex biological structures in 3D.<n>Training a segmentation model requires dense annotations in the upsampled space, a prohibitive labeling burden.<n>We present an end-to-end, GPU-accelerated framework that overcomes this without additional annotations.
  arXiv  Detail & Related papers  (2026-08-04T18:28:19Z)
• Toward Geometry-Scalable Whole-Body Touch for Humanoids: A 3D-Printed Conformal EIT Skin [66.36050076244905]
  Whole-body tactile sensing is a prerequisite for humanoids that operate in contact-rich human environments.<n>We present a conformal electrical tactile tomography skin fabricated through a geometry-adaptable additive-manufacturing workflow.
  arXiv  Detail & Related papers  (2026-08-03T11:33:30Z)
• Point Cloud Diffusion with Global and Local Reconstruction for Instance-Level 3D Anomaly Detection [53.26344422459608]
  We propose textbfPCDiff, a point cloud diffusion framework for instance-level 3D anomaly generation and detection.<n>In the generation phase, an instance-level multi-modal attention is embedded into the generation framework, where anomalies are conditioned with texture gradient, image patch, text and mask.<n>In the detection phase, a joint local-global reconstruction algorithm is introduced to ensure local anomaly restoration and global geometric consistency.
  arXiv  Detail & Related papers  (2026-06-24T12:11:05Z)
• Surface-Constrained Offline Warping with Contact-Aware Online Pose Projection for Safe Robotic Trajectory Execution [2.192782571038966]
  We present a two-stage framework that separates geometric embedding from execution-level regulation.<n>Experiments across multiple analytic surface families and real-robot validation on a sinusoidal surface demonstrate improved geometric continuity, reduced large orientation jumps, and robust contact maintenance.
  arXiv  Detail & Related papers  (2026-03-17T21:54:54Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation [57.06461272772509]
  StdGEN++ is a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs.<n>It achieves state-of-the-art performance, significantly outperforming existing methods in geometric accuracy and semantic disentanglement.<n>The resulting structural independence unlocks advanced downstream capabilities, including non-destructive editing, physics-compliant animation, and gaze tracking.
  arXiv  Detail & Related papers  (2026-01-12T15:41:27Z)
• Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection [64.0168648353038]
  3D anomaly detection in point-cloud data is critical for industrial quality control, aiming to identify structural defects with high reliability.<n>Current memory bank-based methods often suffer from inconsistent feature transformations and limited discriminative capacity.<n>We propose a registration-induced, rotation-invariant feature extraction framework that integrates the objectives of point-cloud registration and memory-based anomaly detection.
  arXiv  Detail & Related papers  (2025-10-19T14:56:38Z)
• G4Splat: Geometry-Guided Gaussian Splatting with Generative Prior [53.762256749551284]
  We identify accurate geometry as the fundamental prerequisite for effectively exploiting generative models to enhance 3D scene reconstruction.<n>We incorporate this geometry guidance throughout the generative pipeline to improve visibility mask estimation, guide novel view selection, and enhance multi-view consistency when inpainting with video diffusion models.<n>Our method naturally supports single-view inputs and unposed videos, with strong generalizability in both indoor and outdoor scenarios.
  arXiv  Detail & Related papers  (2025-10-14T03:06:28Z)
• Limited-Angle Tomography Reconstruction via Projector Guided 3D Diffusion [26.292892614609283]
  Limited-angle electron tomography aims to reconstruct 3D shapes from 2D projections of Transmission Electron Microscopy (TEM) within a restricted range and number of tilting angles.<n>Deep learning approaches have shown promising results in alleviating these artifacts.<n>We propose TEMDiff, a novel 3D diffusion-based iterative reconstruction framework.
  arXiv  Detail & Related papers  (2025-10-07T23:27:28Z)
• Bridging 3D Anomaly Localization and Repair via High-Quality Continuous Geometric Representation [1.4763103835215192]
  New framework integrates 3D anomaly detection and repair by learning a continuous, pose-invariant shape representation.<n>Experiments on Real3D-AD and Anomaly-ShapeNet demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-30T10:11:49Z)
• Geometric Prior-Guided Neural Implicit Surface Reconstruction in the Wild [13.109693095684921]
  We introduce a novel approach that applies multiple geometric constraints to the implicit surface optimization process.<n>First, we utilize sparse 3D points from structure-from-motion (SfM) to refine the signed distance function estimation for the reconstructed surface.<n>We also employ robust normal priors derived from a normal predictor, enhanced by edge prior filtering and multi-view consistency constraints.
  arXiv  Detail & Related papers  (2025-05-12T09:17:30Z)
• GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering [69.67264955234494]
  GeoSplatting is a novel approach that augments 3DGS with explicit geometry guidance for precise light transport modeling.<n>By differentiably constructing a surface-grounded 3DGS from an optimizable mesh, our approach leverages well-defined mesh normals and the opaque mesh surface.<n>This enhancement ensures precise material decomposition while preserving the efficiency and high-quality rendering capabilities of 3DGS.
  arXiv  Detail & Related papers  (2024-10-31T17:57:07Z)
• Improving Gaussian Splatting with Localized Points Management [52.009874685460694]
  Localized Point Management (LPM) is capable of identifying those error-contributing zones in greatest need for both point addition and geometry calibration.<n>LPM applies point densification in the identified zones and then reset the opacity of the points in front of these regions, creating a new opportunity to correct poorly conditioned points.<n> Notably, LPM improves both static 3DGS and dynamic SpaceTimeGS to achieve state-of-the-art rendering quality while retaining real-time speeds.
  arXiv  Detail & Related papers  (2024-06-06T16:55:07Z)
• Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
  We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization. Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information. Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
  arXiv  Detail & Related papers  (2024-05-23T14:39:52Z)
• Cryo-forum: A framework for orientation recovery with uncertainty measure with the application in cryo-EM image analysis [0.0]
  This paper introduces a novel approach that uses a 10-dimensional feature vector to represent the orientation and applies a Quadratically-Constrained Quadratic Program to derive the predicted orientation as a unit quaternion, supplemented by an uncertainty metric. Our numerical analysis demonstrates that our methodology effectively recovers orientations from 2D cryo-EM images in an end-to-end manner. Importantly, the inclusion of uncertainty allows for direct clean-up of the dataset at the 3D level.
  arXiv  Detail & Related papers  (2023-07-19T09:09:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.